This useful book demonstrates how deep learning has advanced machine learning as a whole. Now, even programmers with little to no experience with the technology can implement programmes that can learn from data by using quick, effective tools. Starting with straightforward linear regression and working your way up to deep neural networks, you’ll study a variety of strategies. You’ll pick up tips on how to scale and train deep neural networks. You will investigate a number of training models, such as ensemble approaches, random forests, decision trees, and support vector machines. Starting with straightforward linear regression and working your way up to deep neural networks, you’ll study a variety of strategies. All you need to get started is some programming expertise, and there are exercises in every chapter to help you put what you’ve learned into practise.
Scikit-learn vs TensorFlow:
Machine learning libraries are available for a variety of uses, including categorising, forecasting, computer vision, and AI-powered tools, to mention a few. You must select the appropriate tool if you wish to use these libraries to build applications or address issues.
A popular open source machine learning library for Python is called Scikit-learn. It is accessible and versatile since it is built on top of and integrates with widely used libraries like NumPy, SciPy, Matplotlib, and pandas.
If you’re new to machine learning or creating something with non-neural network algorithms, take a look at scikit-learn.
If you wish to employ a deep learning approach along with hardware acceleration via GPUs and TPUs, or on a cluster of computers (which scikit-learn doesn’t natively support), take a look at TensorFlow.
Topics covered by this book:
- Chapter 1 is about The Machine Learning Landscape
- Chapter 2 is End-to-End Machine Learning Project
- Chapter 3 is about Classification
- Chapter 4 explains us different Training Models
- Chapter 5 describes what are Support Vector Machines
- Chapter 6 is about what are Decision Trees
- Chapter 7 is know as Ensemble Learning and Random Forests
- Chapter 8 is about the Dimensionality Reduction
- Chapter 9 describes Unsupervised Learning Techniques
- Chapter 10 give us Introduction to Artificial Neural Networks with Keras
- Chapter 11 explains Training Deep Neural Networks
- Chapter 12 is Custom Models and Training with Tensor Flow
- Chapter 13 is about Loading and Preprocessing Data with TensorFlow
- Chapter 14 is Deep Computer Vision Using Convolutional Neural Networks
- Chapter 15 is about Processing Sequences Using RNNs and CNNs
- Chapter 16 explains Natural Language Processing with RNNs and Attention
- Chapter 17 represents Representation Learning and Generative Learning Using Auto encoders and GANs
- Chapter 18 is Reinforcement Learning
- Chapter 19 is about Training and Deploying TensorFlow Models at Scale